Information processing device, production facility monitoring method, and computer-readable recording medium recording production facility monitoring program
An information processing device includes: a memory; and a processor coupled to the memory and configured to: learn a classification rule that classifies an abnormal degree of a production facility from a text feature amount based on the text feature amount obtained from a number of texts included in a plurality of pieces of log data obtained in a predetermined process of the production facility and production history information of the production facility; extract a text feature amount of log data to be monitored obtained in the predetermined process of the production facility; and determine an abnormal degree of the production facility when the log data to be monitored is obtained based on the text feature amount and the classification rule.
1. An information processing device comprising:
a memory; and
a processor coupled to the memory and configured to:
learn a classification rule that classifies an abnormal degree of a production facility from a text feature amount based on the text feature amount obtained from a number of texts included in a plurality of pieces of log data obtained in a predetermined process of the production facility and production history information of the production facility;
extract a text feature amount of log data to be monitored obtained in the predetermined process of the production facility; and
determine an abnormal degree of the production facility when the log data to be monitored is obtained based on the text feature amount and the classification rule.
2. The information processing device according to claim 1 , wherein
the text feature amount is obtained from at least one item of a number of characters of a text included in the log data, a number of bytes of the text included in the log data, a number of lines of the log data, a number of types of texts included in the log data, a number of characters of each numerical character included in the log data, a number of characters of each alphabetic character included in the log data, a number of characters of each symbol included in the log data, and a number of characters of each Japanese character included in the log data.
3. The information processing device according to claim 2 , wherein
the text feature amount is a main component of a vector obtained by aggregating two or more of the above items.
4. The information processing device according to claim 2 , wherein
the text feature amount is one of a difference and a correlation coefficient of the item of the log data obtained in the predetermined process that is continuously executed.
5. The information processing device according to claim 1 , wherein the processor is configured to determine a classification rule used for determination by generating a plurality of classification rules based on different text feature amounts and performing cross-validation on the plurality of classification rules.
6. A production facility monitoring comprising:
Learning, by a computer, a classification rule that classifies an abnormal degree of a production facility from a text feature amount based on the text feature amount obtained from a number of texts included in a plurality of pieces of log data obtained in a predetermined process of the production facility and production history information of the production facility;
extracting a text feature amount of log data to be monitored obtained in the predetermined process of the production facility; and
determining an abnormal degree of the production facility when the log data to be monitored is obtained based on the extracted text feature amount and the classification rule.
7. The production facility monitoring method according to claim 6 , wherein
the text feature amount is obtained from at least one item of a number of characters of a text included in the log data, a number of bytes of the text included in the log data, a number of lines of the log data, a number of types of texts included in the log data, a number of characters of each numerical character included in the log data, a number of characters of each alphabetic character included in the log data, a number of characters of each symbol included in the log data, and a number of characters of each Japanese character included in the log data.
8. The production facility monitoring method according to claim 7 , wherein
the text feature amount is a main component of a vector obtained by aggregating two or more of the above items.
9. The production facility monitoring method according to claim 7 , wherein
the text feature amount is one of a difference and a correlation coefficient of the item of the log data obtained in the predetermined process that is continuously executed.
10. The production facility monitoring method according to claim 6 , wherein
in the learning processing, a classification rule used for determination is determined by generating a plurality of classification rules based on different text feature amounts and performing cross-validation on the plurality of classification rules.
11. A non-transitory computer-readable recording medium recording a production facility monitoring program causing a computer to execute processing comprising:
learning a classification rule that classifies an abnormal degree of the production facility from a text feature amount based on the text feature amount obtained from a number of texts included in a plurality of pieces of log data obtained in a predetermined process of the production facility and production history information of the production facility;
extracting a text feature amount of log data to be monitored obtained in the predetermined process of the production facility; and
determining an abnormal degree of the production facility when the log data to be monitored is obtained based on the extracted text feature amount and the classification rule.